東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Digital watermarking for machine lea...

Fan, Lixin.

FindBook

Google Book

Amazon

博客來

Digital watermarking for machine learning model = techniques, protocols and applications /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Digital watermarking for machine learning model/ edited by Lixin Fan, Chee Seng Chan, Qiang Yang.
其他題名:	techniques, protocols and applications /
其他作者:	Fan, Lixin.
出版者:	Singapore :Springer Nature Singapore : : 2023.,
面頁冊數:	1 online resource (xvi, 225 p.) :ill., digital ;24 cm.
內容註:	Part I. Preliminary -- Chapter 1. Introduction -- Chapter 2. Ownership Verification Protocols for Deep Neural Network Watermarks -- Part II Techniques -- Chapter 3. ModelWatermarking for Image Recovery DNNs -- Chapter 4. The Robust and Harmless ModelWatermarking -- Chapter 5. Protecting Intellectual Property of Machine Learning Models via Fingerprinting the Classification Boundary -- Chapter 6. Protecting Image Processing Networks via Model Water -- Chapter 7. Watermarks for Deep Reinforcement Learning -- Chapter 8. Ownership Protection for Image Captioning Models -- Chapter 9.Protecting Recurrent Neural Network by Embedding Key -- Part III Applications -- Chapter 10. FedIPR: Ownership Verification for Federated Deep Neural Network Models -- Chapter 11. Model Auditing For Data Intellectual Property.
Contained By:	Springer Nature eBook
標題:	Digital watermarking. -
電子資源:	https://doi.org/10.1007/978-981-19-7554-7
ISBN:	9789811975547

Digital watermarking for machine learning model = techniques, protocols and applications /
Digital watermarking for machine learning modeltechniques, protocols and applications /[electronic resource] :edited by Lixin Fan, Chee Seng Chan, Qiang Yang. - Singapore :Springer Nature Singapore :2023. - 1 online resource (xvi, 225 p.) :ill., digital ;24 cm.

Part I. Preliminary -- Chapter 1. Introduction -- Chapter 2. Ownership Verification Protocols for Deep Neural Network Watermarks -- Part II Techniques -- Chapter 3. ModelWatermarking for Image Recovery DNNs -- Chapter 4. The Robust and Harmless ModelWatermarking -- Chapter 5. Protecting Intellectual Property of Machine Learning Models via Fingerprinting the Classification Boundary -- Chapter 6. Protecting Image Processing Networks via Model Water -- Chapter 7. Watermarks for Deep Reinforcement Learning -- Chapter 8. Ownership Protection for Image Captioning Models -- Chapter 9.Protecting Recurrent Neural Network by Embedding Key -- Part III Applications -- Chapter 10. FedIPR: Ownership Verification for Federated Deep Neural Network Models -- Chapter 11. Model Auditing For Data Intellectual Property.

Machine learning (ML) models, especially large pretrained deep learning (DL) models, are of high economic value and must be properly protected with regard to intellectual property rights (IPR) Model watermarking methods are proposed to embed watermarks into the target model, so that, in the event it is stolen, the model's owner can extract the pre-defined watermarks to assert ownership. Model watermarking methods adopt frequently used techniques like backdoor training, multi-task learning, decision boundary analysis etc. to generate secret conditions that constitute model watermarks or fingerprints only known to model owners. These methods have little or no effect on model performance, which makes them applicable to a wide variety of contexts. In terms of robustness, embedded watermarks must be robustly detectable against varying adversarial attacks that attempt to remove the watermarks. The efficacy of model watermarking methods is showcased in diverse applications including image classification, image generation, image captions, natural language processing and reinforcement learning. This book covers the motivations, fundamentals, techniques and protocols for protecting ML models using watermarking. Furthermore, it showcases cutting-edge work in e.g. model watermarking, signature and passport embedding and their use cases in distributed federated learning settings.

ISBN: 9789811975547

Standard No.: 10.1007/978-981-19-7554-7doiSubjects--Topical Terms:

629095
Digital watermarking.

LC Class. No.: QA76.9.A25

Dewey Class. No.: 005.82

Digital watermarking for machine learning model = techniques, protocols and applications /
LDR:03258nmm a2200325 a 4500 001 2318537
003 DE-He213
005 20230529115623.0
006 m d
007 cr nn 008maaau
008 230902s2023 si s 0 eng d
020 $a 9789811975547 $q (electronic bk.)
020 $a 9789811975530 $q (paper)
024 7 $a 10.1007/978-981-19-7554-7 $2 doi
035 $a 978-981-19-7554-7
040 $a GP $c GP
041 0 $a eng
050 4 $a QA76.9.A25
072 7 $a UYQM $2 bicssc
072 7 $a COM004000 $2 bisacsh
072 7 $a UYQM $2 thema
082 0 4 $a 005.82 $2 23
090 $a QA76.9.A25 $b D574 2023
245 0 0 $a Digital watermarking for machine learning model $h [electronic resource] : $b techniques, protocols and applications / $c edited by Lixin Fan, Chee Seng Chan, Qiang Yang.
260 $a Singapore : $b Springer Nature Singapore : $b Imprint: Springer, $c 2023.
300 $a 1 online resource (xvi, 225 p.) : $b ill., digital ; $c 24 cm.
505 0 $a Part I. Preliminary -- Chapter 1. Introduction -- Chapter 2. Ownership Verification Protocols for Deep Neural Network Watermarks -- Part II Techniques -- Chapter 3. ModelWatermarking for Image Recovery DNNs -- Chapter 4. The Robust and Harmless ModelWatermarking -- Chapter 5. Protecting Intellectual Property of Machine Learning Models via Fingerprinting the Classification Boundary -- Chapter 6. Protecting Image Processing Networks via Model Water -- Chapter 7. Watermarks for Deep Reinforcement Learning -- Chapter 8. Ownership Protection for Image Captioning Models -- Chapter 9.Protecting Recurrent Neural Network by Embedding Key -- Part III Applications -- Chapter 10. FedIPR: Ownership Verification for Federated Deep Neural Network Models -- Chapter 11. Model Auditing For Data Intellectual Property.
520 $a Machine learning (ML) models, especially large pretrained deep learning (DL) models, are of high economic value and must be properly protected with regard to intellectual property rights (IPR) Model watermarking methods are proposed to embed watermarks into the target model, so that, in the event it is stolen, the model's owner can extract the pre-defined watermarks to assert ownership. Model watermarking methods adopt frequently used techniques like backdoor training, multi-task learning, decision boundary analysis etc. to generate secret conditions that constitute model watermarks or fingerprints only known to model owners. These methods have little or no effect on model performance, which makes them applicable to a wide variety of contexts. In terms of robustness, embedded watermarks must be robustly detectable against varying adversarial attacks that attempt to remove the watermarks. The efficacy of model watermarking methods is showcased in diverse applications including image classification, image generation, image captions, natural language processing and reinforcement learning. This book covers the motivations, fundamentals, techniques and protocols for protecting ML models using watermarking. Furthermore, it showcases cutting-edge work in e.g. model watermarking, signature and passport embedding and their use cases in distributed federated learning settings.
650 0 $a Digital watermarking. $3 629095
650 0 $a Machine learning $x Safety measures. $3 3630740
650 1 4 $a Machine Learning. $3 3382522
650 2 4 $a Data and Information Security. $3 3538510
650 2 4 $a Computer Imaging, Vision, Pattern Recognition and Graphics. $3 890871
650 2 4 $a Image Processing. $3 891209
700 1 $a Fan, Lixin. $3 3527696
700 1 $a Chan, Chee Seng. $3 3529480
700 1 $a Yang, Qiang. $3 1678660
710 2 $a SpringerLink (Online service) $3 836513
773 0 $t Springer Nature eBook
856 4 0 $u https://doi.org/10.1007/978-981-19-7554-7
950 $a Computer Science (SpringerNature-11645)